基于深度学习的医学图像分割研究进展
|
摘要
医学图像分割是医学图像定量分析的关键步骤之一,因此病灶分割对临床诊断有重要意义。针对传统分割方法中存在的过多依赖医学领域的先验知识和人为评估错误等问题,提出了基于深度学习的病灶分割方法。本文总结了卷积神经网络算法应用于医学图像病灶分割的研究进展。首先,论述卷积神经网络的基本结构及其常用架构;其次介绍深度学习在医学图像病灶分割中的应用,其中包括肺结节的检测和分类,脑肿瘤分割和乳腺病灶的分割;最后,分析了目前该研究中存在的优缺点并对深度学习的发展方向进行展望。
Medical image segmentation is a key step in the quantitative analysis of medical images. Therefore, segmentation of lesions is of great significance for clinical diagnosis. Based on the problems of traditional segmentation methods such as excessive dependence on the prior knowledge of medical science and errors in subjective assessment, the researchers propose a deep learningbased method for lesion segmentation. Herein the research progress of convolutional neural network algorithm in lesion segmentation is summarized. First, the basic structure and architecture of convolutional neural network are expounded. Secondly,the application of deep learning in lesion segmentation, including the detection and classification of pulmonary nodules and the segmentation of brain tumors and breast lesions, are introduced. Finally, the advantages and disadvantages existed in this research are analyzed and the development direction of deep learning is prospected.
Medical image segmentation is a key step in the quantitative analysis of medical images. Therefore, segmentation of lesions is of great significance for clinical diagnosis. Based on the problems of traditional segmentation methods such as excessive dependence on the prior knowledge of medical science and errors in subjective assessment, the researchers propose a deep learningbased method for lesion segmentation. Herein the research progress of convolutional neural network algorithm in lesion segmentation is summarized. First, the basic structure and architecture of convolutional neural network are expounded. Secondly,the application of deep learning in lesion segmentation, including the detection and classification of pulmonary nodules and the segmentation of brain tumors and breast lesions, are introduced. Finally, the advantages and disadvantages existed in this research are analyzed and the development direction of deep learning is prospected.
引文
[1] ZANATY E A, GHONIEMY S. Medical image segmentation techniques:an overview[J]. Int J Informatics Medi Data Process,2016, 1(1):16-37.
[2] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015,521(7553):436.
[3] ZHANG L, LU L, NOGUES I, et al. DeepPap:deep convolutional networks for cervical cell classification[J]. IEEE J Biomed Health Inform, 2017, 21(6):1633-1643.
[4]周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报, 2017,40(6):1229-1251.ZHOU F Y, JIN L P, DONG J. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40(6):1229-1251.
[5] PAI A, TENG Y C, BLAIR J, et al. Chapter 10-characterization of errors in deep learning-based brain MRI segmentation[M]//Deep Learning for Medical Image Analysis. Cambridge, Massachusetts:Academic Press, 2017:223-242.
[6] AKKUS Z, GALIMZIANOVAA, HOOGI A, et al. Deep learning for brain MRI segmentation:state of the art and future directions[J]. J Digit Imaging, 2017, 30(4):449-459.
[7] PEREIRA S, PINTO A, ALVES V, et al. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Trans Med Imaging, 2016, 35(5):1240-1251.
[8] NYúL L G, UDUPA J K. On standardizing the MR image intensity scale[J]. Magn Reson Med, 1999, 42(6):1072-1081.
[9] SHIN G S, KIM D H, LEE J H, et al. Method and apparatus for blockbased image denoising:US8818126[P]. 2014-08-26.
[10]REN S, GIRSHICK R, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(6):1137-1149.
[11]REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems. Cambridge,Massachusetts:MIT Press, 2015:91-99.
[12]HUA K L, HSU C H, HIDAYATI S C, et al. Computer-aided classification of lung nodules on computed tomography images via deep learning technique[J]. Onco Targets Ther, 2015, 8:2015-2022.
[13]CHENG J Z, NI D, CHOU Y H, et al. Computer-aided diagnosis with deep learning architecture:applications to breast lesions in US images and pulmonary nodules in CT scans[J]. Sci Rep, 2016, 6:24454.
[14]CIOMPI F, CHUNG K, RIEL S J, et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning[J].Sci Rep, 2017, 7:46479.
[15]LIAUCHUK V, KOVALEV V, KALINOVSKY A, et al. Examining the ability of convolutional neural networks to detect lesions in lung CT images(deep learning)[C]//Computer Assisted Radiology and Surgery. Barcelona, 2017.
[16]HAVAEI M, DAVY A, WARDE-FARLEY D, et al. Brain tumor segmentation with deep neural networks[J]. Med Image Anal, 2017,35:18-31.
[17]PEREIRA S, PINTO A, ALVES V, et al. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Trans Med Imaging, 2016, 35(5):1240-1251.
[18]ZHANG W, LI R, DENG H, et al. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation[J].Neuroimage, 2015, 108:214-224.
[19]NIE D, WANG L, GAO Y, et al. Fully convolutional networks for multimodality isointense infant brain image segmentation[C]//2016 IEEE13th International Symposium on Biomedical Imaging(ISBI). IEEE,2016:1342-1345.
[20]MOESKOPS P, VIERGEVER M A, MENDRIK A M, et al.Automatic segmentation of MR brain images with a convolutional neural network[J]. IEEE Trans Med Imaging, 2016, 35(5):1252-1261.
[21]SIEGEL R L, MILLER K D, AHMEDIN JEMAL D V. Cancer statistics, 2018[J]. Ca Cancer J Clin, 2018, 68:7-30.
[22]DHUNGEL N, CARNEIRO G, BRADLEY A P. Deep structured learning for mass segmentation from mammograms[C]//IEEE International Conference on Image Processing. IEEE, 2015:2950-2954.
[23]XU J, XIANG L, LIU Q, et al. Stacked sparse autoencoder(SSAE)for nuclei detection on breast cancer histopathology images[J]. IEEE Trans Med Imaging, 2016, 35(1):119-130.
[24]LIU X, SHI J, ZHANG Q. Tumor classification by deep polynomial network and multiple kernel learning on small ultrasound image dataset[M]//Machine Learning in Medical Imaging. New York:Springer International Publishing, 2015:313-320.
[2] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015,521(7553):436.
[3] ZHANG L, LU L, NOGUES I, et al. DeepPap:deep convolutional networks for cervical cell classification[J]. IEEE J Biomed Health Inform, 2017, 21(6):1633-1643.
[4]周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报, 2017,40(6):1229-1251.ZHOU F Y, JIN L P, DONG J. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40(6):1229-1251.
[5] PAI A, TENG Y C, BLAIR J, et al. Chapter 10-characterization of errors in deep learning-based brain MRI segmentation[M]//Deep Learning for Medical Image Analysis. Cambridge, Massachusetts:Academic Press, 2017:223-242.
[6] AKKUS Z, GALIMZIANOVAA, HOOGI A, et al. Deep learning for brain MRI segmentation:state of the art and future directions[J]. J Digit Imaging, 2017, 30(4):449-459.
[7] PEREIRA S, PINTO A, ALVES V, et al. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Trans Med Imaging, 2016, 35(5):1240-1251.
[8] NYúL L G, UDUPA J K. On standardizing the MR image intensity scale[J]. Magn Reson Med, 1999, 42(6):1072-1081.
[9] SHIN G S, KIM D H, LEE J H, et al. Method and apparatus for blockbased image denoising:US8818126[P]. 2014-08-26.
[10]REN S, GIRSHICK R, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(6):1137-1149.
[11]REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems. Cambridge,Massachusetts:MIT Press, 2015:91-99.
[12]HUA K L, HSU C H, HIDAYATI S C, et al. Computer-aided classification of lung nodules on computed tomography images via deep learning technique[J]. Onco Targets Ther, 2015, 8:2015-2022.
[13]CHENG J Z, NI D, CHOU Y H, et al. Computer-aided diagnosis with deep learning architecture:applications to breast lesions in US images and pulmonary nodules in CT scans[J]. Sci Rep, 2016, 6:24454.
[14]CIOMPI F, CHUNG K, RIEL S J, et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning[J].Sci Rep, 2017, 7:46479.
[15]LIAUCHUK V, KOVALEV V, KALINOVSKY A, et al. Examining the ability of convolutional neural networks to detect lesions in lung CT images(deep learning)[C]//Computer Assisted Radiology and Surgery. Barcelona, 2017.
[16]HAVAEI M, DAVY A, WARDE-FARLEY D, et al. Brain tumor segmentation with deep neural networks[J]. Med Image Anal, 2017,35:18-31.
[17]PEREIRA S, PINTO A, ALVES V, et al. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Trans Med Imaging, 2016, 35(5):1240-1251.
[18]ZHANG W, LI R, DENG H, et al. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation[J].Neuroimage, 2015, 108:214-224.
[19]NIE D, WANG L, GAO Y, et al. Fully convolutional networks for multimodality isointense infant brain image segmentation[C]//2016 IEEE13th International Symposium on Biomedical Imaging(ISBI). IEEE,2016:1342-1345.
[20]MOESKOPS P, VIERGEVER M A, MENDRIK A M, et al.Automatic segmentation of MR brain images with a convolutional neural network[J]. IEEE Trans Med Imaging, 2016, 35(5):1252-1261.
[21]SIEGEL R L, MILLER K D, AHMEDIN JEMAL D V. Cancer statistics, 2018[J]. Ca Cancer J Clin, 2018, 68:7-30.
[22]DHUNGEL N, CARNEIRO G, BRADLEY A P. Deep structured learning for mass segmentation from mammograms[C]//IEEE International Conference on Image Processing. IEEE, 2015:2950-2954.
[23]XU J, XIANG L, LIU Q, et al. Stacked sparse autoencoder(SSAE)for nuclei detection on breast cancer histopathology images[J]. IEEE Trans Med Imaging, 2016, 35(1):119-130.
[24]LIU X, SHI J, ZHANG Q. Tumor classification by deep polynomial network and multiple kernel learning on small ultrasound image dataset[M]//Machine Learning in Medical Imaging. New York:Springer International Publishing, 2015:313-320.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |